Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The electrician, a burly fellow with a thick mustache, had paused mid-sentence, his eyes flicking around the room. "Didn't you know? That's where they found the…you know." He gestured vaguely towards the kitchen, a space he’d just been admiring for its cleanliness. The homeowner, Kevin, had prided himself on the gleaming appliances.

Kevin was struck silent, a strange pressure building in his head. He'd been looking forward to moving in, making the home his own. Now, he felt a sudden sense of revulsion toward the kitchen, toward the whole house. He'd imagined family dinners, laughter, and warmth.

He turned away from the electrician, unable to meet his gaze. He began walking. Fast. His steps grew quicker as he crossed the yard, his hands clenched into fists. He had to escape, to be free from this burden.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

This story is one of 1,000 stories generated for the emotion insulted. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 insulted stories, after denoising with neutral dialogue baselines, produces the insulted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the insulted vector is projected through the unembedding matrix.

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217